Drishti दृष्टि Live signals →

Home › Story

We let an AI issue 612 crypto signals — the honest scorecard

What happens when an AI issues thousands of crypto signals in public?

We pointed a large language model at live crypto markets, had it issue a directional signal with entry, stop-loss and take-profit about every 15 minutes, and published every single outcome — no deletions. After 612 signals the honest scorecard is a 50.7% win rate at 1.28 average reward-to-risk and a 2.14 Sharpe ratio. Here's what the data shows.

Updated 2026-07-19 · 612 signals tracked

The setup

Every ~15 minutes, an AI model (Anthropic Claude) reads dozens of live features per asset — momentum, order flow, funding, open interest, volatility, macro — and decides whether there's a risk-defined trade worth taking on Bitcoin, Ethereum and other perpetual futures. Each call is a clean, testable trade: entry, stop-loss, take-profit.

The honest scorecard

Across 612 closed signals: 50.7% win rate, 1.28 average reward-to-risk, 2.14 Sharpe. Not every trade wins — and crucially, the losers are all still on the record. A positive average reward-to-risk above 1 with a win rate near 50% is a genuinely positive-expectancy result, and it is fully auditable in the track record.

What we learned

See for yourself

Watch the live signals on the dashboard, download the raw CSV, or read how accurate are AI trading signals.

FAQ

Do AI crypto signals actually work?

Drishti's 612-signal public record shows a 50.7% win rate at 1.28 average reward-to-risk — a positive-expectancy result, with every losing trade included.

How many crypto signals has Drishti published?

612 and counting, each one scored a win or loss on a permanent public ledger — none deleted.

See Drishti's live signals Get the app

Educational & illustrative only — not investment advice. Drishti publishes AI-generated trade ideas and their public track record for information. Crypto is volatile and you can lose money. Nothing here is a recommendation to buy or sell any asset. Do your own research.